From 03d97c104f2d68cffd1bfc48cd62727e13a64712 Mon Sep 17 00:00:00 2001
From: Rui Miguel Silva <rui.silva@linaro.org>
Date: Fri, 14 Oct 2022 17:42:52 +0100
Subject: [PATCH] newlib: memcpy: remove optimized version

When creating messages packed to send over openamp we may need
to do some copy in unaligned address, because of that we may
not always use the assembler optimized version, which will
trough a data-abort on aligned address exception.

So, we may just use the version in string.h (the same used in
optee-os) that will take care to check and use different
optimization based on given source or destination address's.

Upstream-Status: Pending
Signed-off-by: Rui Miguel Silva <rui.silva@linaro.org>
---
 newlib/libc/machine/aarch64/memcpy-stub.c |   2 +-
 newlib/libc/machine/aarch64/memcpy.S      | 166 ----------------------
 2 files changed, 1 insertion(+), 167 deletions(-)

diff --git a/newlib/libc/machine/aarch64/memcpy-stub.c b/newlib/libc/machine/aarch64/memcpy-stub.c
index cd6d72a8b8af..5f2b7968c7fc 100644
--- a/newlib/libc/machine/aarch64/memcpy-stub.c
+++ b/newlib/libc/machine/aarch64/memcpy-stub.c
@@ -27,5 +27,5 @@
 #if (defined (__OPTIMIZE_SIZE__) || defined (PREFER_SIZE_OVER_SPEED))
 # include "../../string/memcpy.c"
 #else
-/* See memcpy.S  */
+# include "../../string/memcpy.c"
 #endif
diff --git a/newlib/libc/machine/aarch64/memcpy.S b/newlib/libc/machine/aarch64/memcpy.S
index 463bad0a1816..2a1460546374 100644
--- a/newlib/libc/machine/aarch64/memcpy.S
+++ b/newlib/libc/machine/aarch64/memcpy.S
@@ -61,170 +61,4 @@
 #if (defined (__OPTIMIZE_SIZE__) || defined (PREFER_SIZE_OVER_SPEED))
 /* See memcpy-stub.c  */
 #else
-
-#define dstin	x0
-#define src	x1
-#define count	x2
-#define dst	x3
-#define srcend	x4
-#define dstend	x5
-#define A_l	x6
-#define A_lw	w6
-#define A_h	x7
-#define A_hw	w7
-#define B_l	x8
-#define B_lw	w8
-#define B_h	x9
-#define C_l	x10
-#define C_h	x11
-#define D_l	x12
-#define D_h	x13
-#define E_l	src
-#define E_h	count
-#define F_l	srcend
-#define F_h	dst
-#define tmp1	x9
-
-#define L(l) .L ## l
-
-	.macro def_fn f p2align=0
-	.text
-	.p2align \p2align
-	.global \f
-	.type \f, %function
-\f:
-	.endm
-
-/* Copies are split into 3 main cases: small copies of up to 16 bytes,
-   medium copies of 17..96 bytes which are fully unrolled. Large copies
-   of more than 96 bytes align the destination and use an unrolled loop
-   processing 64 bytes per iteration.
-   Small and medium copies read all data before writing, allowing any
-   kind of overlap, and memmove tailcalls memcpy for these cases as
-   well as non-overlapping copies.
-*/
-
-def_fn memcpy p2align=6
-	prfm	PLDL1KEEP, [src]
-	add	srcend, src, count
-	add	dstend, dstin, count
-	cmp	count, 16
-	b.ls	L(copy16)
-	cmp	count, 96
-	b.hi	L(copy_long)
-
-	/* Medium copies: 17..96 bytes.  */
-	sub	tmp1, count, 1
-	ldp	A_l, A_h, [src]
-	tbnz	tmp1, 6, L(copy96)
-	ldp	D_l, D_h, [srcend, -16]
-	tbz	tmp1, 5, 1f
-	ldp	B_l, B_h, [src, 16]
-	ldp	C_l, C_h, [srcend, -32]
-	stp	B_l, B_h, [dstin, 16]
-	stp	C_l, C_h, [dstend, -32]
-1:
-	stp	A_l, A_h, [dstin]
-	stp	D_l, D_h, [dstend, -16]
-	ret
-
-	.p2align 4
-	/* Small copies: 0..16 bytes.  */
-L(copy16):
-	cmp	count, 8
-	b.lo	1f
-	ldr	A_l, [src]
-	ldr	A_h, [srcend, -8]
-	str	A_l, [dstin]
-	str	A_h, [dstend, -8]
-	ret
-	.p2align 4
-1:
-	tbz	count, 2, 1f
-	ldr	A_lw, [src]
-	ldr	A_hw, [srcend, -4]
-	str	A_lw, [dstin]
-	str	A_hw, [dstend, -4]
-	ret
-
-	/* Copy 0..3 bytes.  Use a branchless sequence that copies the same
-	   byte 3 times if count==1, or the 2nd byte twice if count==2.  */
-1:
-	cbz	count, 2f
-	lsr	tmp1, count, 1
-	ldrb	A_lw, [src]
-	ldrb	A_hw, [srcend, -1]
-	ldrb	B_lw, [src, tmp1]
-	strb	A_lw, [dstin]
-	strb	B_lw, [dstin, tmp1]
-	strb	A_hw, [dstend, -1]
-2:	ret
-
-	.p2align 4
-	/* Copy 64..96 bytes.  Copy 64 bytes from the start and
-	   32 bytes from the end.  */
-L(copy96):
-	ldp	B_l, B_h, [src, 16]
-	ldp	C_l, C_h, [src, 32]
-	ldp	D_l, D_h, [src, 48]
-	ldp	E_l, E_h, [srcend, -32]
-	ldp	F_l, F_h, [srcend, -16]
-	stp	A_l, A_h, [dstin]
-	stp	B_l, B_h, [dstin, 16]
-	stp	C_l, C_h, [dstin, 32]
-	stp	D_l, D_h, [dstin, 48]
-	stp	E_l, E_h, [dstend, -32]
-	stp	F_l, F_h, [dstend, -16]
-	ret
-
-	/* Align DST to 16 byte alignment so that we don't cross cache line
-	   boundaries on both loads and stores.	 There are at least 96 bytes
-	   to copy, so copy 16 bytes unaligned and then align.	The loop
-	   copies 64 bytes per iteration and prefetches one iteration ahead.  */
-
-	.p2align 4
-L(copy_long):
-	and	tmp1, dstin, 15
-	bic	dst, dstin, 15
-	ldp	D_l, D_h, [src]
-	sub	src, src, tmp1
-	add	count, count, tmp1	/* Count is now 16 too large.  */
-	ldp	A_l, A_h, [src, 16]
-	stp	D_l, D_h, [dstin]
-	ldp	B_l, B_h, [src, 32]
-	ldp	C_l, C_h, [src, 48]
-	ldp	D_l, D_h, [src, 64]!
-	subs	count, count, 128 + 16	/* Test and readjust count.  */
-	b.ls	2f
-1:
-	stp	A_l, A_h, [dst, 16]
-	ldp	A_l, A_h, [src, 16]
-	stp	B_l, B_h, [dst, 32]
-	ldp	B_l, B_h, [src, 32]
-	stp	C_l, C_h, [dst, 48]
-	ldp	C_l, C_h, [src, 48]
-	stp	D_l, D_h, [dst, 64]!
-	ldp	D_l, D_h, [src, 64]!
-	subs	count, count, 64
-	b.hi	1b
-
-	/* Write the last full set of 64 bytes.	 The remainder is at most 64
-	   bytes, so it is safe to always copy 64 bytes from the end even if
-	   there is just 1 byte left.  */
-2:
-	ldp	E_l, E_h, [srcend, -64]
-	stp	A_l, A_h, [dst, 16]
-	ldp	A_l, A_h, [srcend, -48]
-	stp	B_l, B_h, [dst, 32]
-	ldp	B_l, B_h, [srcend, -32]
-	stp	C_l, C_h, [dst, 48]
-	ldp	C_l, C_h, [srcend, -16]
-	stp	D_l, D_h, [dst, 64]
-	stp	E_l, E_h, [dstend, -64]
-	stp	A_l, A_h, [dstend, -48]
-	stp	B_l, B_h, [dstend, -32]
-	stp	C_l, C_h, [dstend, -16]
-	ret
-
-	.size	memcpy, . - memcpy
 #endif
-- 
2.38.0